Paper Citation Record · LEDGER

SeWA: Selective Weight Average via Probabilistic Masking

As of 9 August 2026, this Paper Citation Record lists 39 of 39 outbound references and 1 inbound Pith citation observation for arXiv:2502.10119.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2502.10119 v1

Coverage vector

measured 39 of 39 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T19:24:43.420857Z

measured 40 of 40 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-08T06:32:00.761636+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-05-18T13:32:33.009367Z

measured 0 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: arxiv_reference, observed 2026-05-18T13:32:37.730993Z

Reference resolution

39 of 39 outbound references displayed

verified exact3
verified fuzzy23
unresolved13
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 14716e51-ddf6-40b7-8128-2c2c91b120aa · outbound

This paper cites write newline.

SeWA: Selective Weight Average via Probabilistic Masking write newline

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-07T19:24:42.696185Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a922d221-b656-4605-84e5-21f59a7c859b · outbound

This paper cites and Elisseeff, A.

SeWA: Selective Weight Average via Probabilistic Masking and Elisseeff, A

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T19:24:44.837377Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 1f609dcd-fbe0-4c71-9376-aeb48bf320d3 · outbound

This paper cites Swad: Domain generalization by seeking flat minima.

SeWA: Selective Weight Average via Probabilistic Masking Swad: Domain generalization by seeking flat minima

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-07T19:24:42.807326Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f3f129b5-a4fa-4430-bfac-d9b3dd00022c · outbound

This paper cites and Papailiopoulos, D.

SeWA: Selective Weight Average via Probabilistic Masking and Papailiopoulos, D

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T19:24:44.741807Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 8e86d28b-57aa-4942-bf16-263d6ab3326f · outbound

This paper cites and Wagner, T.

SeWA: Selective Weight Average via Probabilistic Masking and Wagner, T

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T19:24:44.694554Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 0a09881a-c0ef-414f-a425-6b83fa861a41 · outbound

This paper cites D4RL: Datasets for Deep Data-Driven Reinforcement Learning.

SeWA: Selective Weight Average via Probabilistic Masking D4RL: Datasets for Deep Data-Driven Reinforcement Learning

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-07T19:24:42.959586Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 87479ca6-fff2-4422-a983-54fd37f65f43 · outbound

This paper cites Train faster, generalize better: Stability of stochastic gradient descent.

SeWA: Selective Weight Average via Probabilistic Masking Train faster, generalize better: Stability of stochastic gradient descent

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T19:24:44.672799Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation fce9a301-c775-4415-926e-77509e0d658d · outbound

This paper cites Meta-learning pac-bayes priors in model averaging.

SeWA: Selective Weight Average via Probabilistic Masking Meta-learning pac-bayes priors in model averaging

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T19:24:44.656789Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 8842ebcc-9397-400f-8cd9-de97074fef9e · outbound

This paper cites Averaging Weights Leads to Wider Optima and Better Generalization.

SeWA: Selective Weight Average via Probabilistic Masking Averaging Weights Leads to Wider Optima and Better Generalization

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-07T19:24:42.975157Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9587ba11-67a2-4ebf-88d0-1da9e795df86 · outbound

This paper cites Categorical reparameterization with gumbel-softmax.

SeWA: Selective Weight Average via Probabilistic Masking Categorical reparameterization with gumbel-softmax

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T19:24:44.641986Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation c82569f7-f37f-4480-a96c-68ad743f8f3e · outbound

This paper cites Stop Wasting My Time! Saving Days of ImageNet and BERT Training with Latest Weight Averaging.

SeWA: Selective Weight Average via Probabilistic Masking Stop Wasting My Time! Saving Days of ImageNet and BERT Training with Latest Weight Averaging

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-07T19:24:42.985303Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 38110354-7403-4ec7-85a9-7af694334703 · outbound

This paper cites Auto-Encoding Variational Bayes.

SeWA: Selective Weight Average via Probabilistic Masking Auto-Encoding Variational Bayes

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-07T19:24:42.990625Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f7655827-9e5f-4a0e-a31c-813bb32d37b8 · outbound

This paper cites and Lampert, C.

SeWA: Selective Weight Average via Probabilistic Masking and Lampert, C

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T19:24:44.626366Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation e7db1f42-5e40-418b-86c7-dd261595de81 · outbound

This paper cites and Ying, Y.

SeWA: Selective Weight Average via Probabilistic Masking and Ying, Y

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T19:24:44.610686Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 46146d92-4d69-4fe0-87cf-36408efc09dd · outbound

This paper cites Trainable weight averaging: Efficient training by optimizing historical solutions.

SeWA: Selective Weight Average via Probabilistic Masking Trainable weight averaging: Efficient training by optimizing historical solutions

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T19:24:44.594735Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 6d2c95c2-08b8-48b1-84b6-3de5d7c99595 · outbound

This paper cites Deep Model Fusion: A Survey.

SeWA: Selective Weight Average via Probabilistic Masking Deep Model Fusion: A Survey

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-07T19:24:43.113821Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bf8478ae-ba25-43d5-ad8e-3a82c9bc3a59 · outbound

This paper cites Improving generalization of pre-trained language models via stochastic weight averaging.

SeWA: Selective Weight Average via Probabilistic Masking Improving generalization of pre-trained language models via stochastic weight averaging

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T19:24:44.580034Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation a93cb507-6aa5-4b74-b500-578c00c8e196 · outbound

This paper cites J., Mnih, A., and Teh, Y.

SeWA: Selective Weight Average via Probabilistic Masking J., Mnih, A., and Teh, Y

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T19:24:44.563834Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 7350354a-0a36-489a-a984-eca0d8e15888 · outbound

This paper cites Learning theory: stability is sufficient for generalization and necessary and sufficient for consistency of empirical risk minimization.

SeWA: Selective Weight Average via Probabilistic Masking Learning theory: stability is sufficient for generalization and necessary and sufficient for consistency of empirical risk minimization

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T19:24:44.547060Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 106b3f35-5faf-42ea-af4b-0a5d93ea7c04 · outbound

This paper cites an unresolved cited work.

SeWA: Selective Weight Average via Probabilistic Masking Unresolved cited work

Reference 20

Resolution: unresolved; raw_fallback, observed 2026-08-07T19:24:44.466457Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation e6d9c2fd-606d-4854-9296-68ba65a86e55 · outbound

This paper cites J., Mohamed, S., and Wierstra, D.

SeWA: Selective Weight Average via Probabilistic Masking J., Mohamed, S., and Wierstra, D

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T19:24:44.361292Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 8c353f1b-a215-4b3c-b4b2-f195edd9a869 · outbound

This paper cites Efficient estimations from a slowly convergent robbins-monro process.

SeWA: Selective Weight Average via Probabilistic Masking Efficient estimations from a slowly convergent robbins-monro process

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T19:24:44.259656Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation d35f4521-7dfc-4412-82ad-9f81c3159dfa · outbound

This paper cites T., Kaddour, J., Kumar, A., et al.

SeWA: Selective Weight Average via Probabilistic Masking T., Kaddour, J., Kumar, A., et al

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T19:24:44.115389Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation bf4c830f-d426-4715-8747-1c5d5ff2305a · outbound

This paper cites Learnability, stability and uniform convergence.

SeWA: Selective Weight Average via Probabilistic Masking Learnability, stability and uniform convergence

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T19:24:44.099889Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation f4108679-09b4-4f18-a724-86fe7beaa733 · outbound

This paper cites Without-replacement sampling for stochastic gradient methods.

SeWA: Selective Weight Average via Probabilistic Masking Without-replacement sampling for stochastic gradient methods

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T19:24:44.083715Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 4094e851-16b1-4eac-b672-20e8a9710a5b · outbound

This paper cites Towards Understanding Generalization and Stability Gaps between Centralized and Decentralized Federated Learning.

SeWA: Selective Weight Average via Probabilistic Masking Towards Understanding Generalization and Stability Gaps between Centralized and Decentralized Federated Learning

Reference 26

Resolution: verified exact; local_arxiv, observed 2026-08-07T19:24:43.610104Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation cf937c0e-33a2-458b-918e-f9e886e1ae5a · outbound

This paper cites Understanding How Consistency Works in Federated Learning via Stage-wise Relaxed Initialization.

SeWA: Selective Weight Average via Probabilistic Masking Understanding How Consistency Works in Federated Learning via Stage-wise Relaxed Initialization

Reference 27

Resolution: verified exact; local_arxiv, observed 2026-08-07T19:24:43.568249Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 7af7c28e-a845-4046-8deb-de7e2dd0c810 · outbound

This paper cites S., McAllester, D., Singh, S., and Mansour, Y.

SeWA: Selective Weight Average via Probabilistic Masking S., McAllester, D., Singh, S., and Mansour, Y

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-07T19:24:43.367976Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e471d9b7-b186-49f9-82d4-4ecac6080962 · outbound

This paper cites Rethinking the inception architecture for computer vision.

SeWA: Selective Weight Average via Probabilistic Masking Rethinking the inception architecture for computer vision

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-07T19:24:43.373286Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 88bab29a-1c1f-4da7-b4dd-a3ae0a8d0541 · outbound

This paper cites Generalization analysis of stochastic weight averaging with general sampling.

SeWA: Selective Weight Average via Probabilistic Masking Generalization analysis of stochastic weight averaging with general sampling

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T19:24:44.047621Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 53032bf2-b992-4817-8fd1-fca6e2dfab3e · outbound

This paper cites A Unified Analysis for Finite Weight Averaging.

SeWA: Selective Weight Average via Probabilistic Masking A Unified Analysis for Finite Weight Averaging

Reference 31

Resolution: verified exact; local_arxiv, observed 2026-08-07T19:24:43.484568Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 90185403-3b63-425c-8cf8-3d44636764d1 · outbound

This paper cites an unresolved cited work.

SeWA: Selective Weight Average via Probabilistic Masking Unresolved cited work

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-07T19:24:43.387306Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 67c3a9c5-8082-420e-8254-daa5e4168adb · outbound

This paper cites Stability analysis and generalization bounds of adversarial training.

SeWA: Selective Weight Average via Probabilistic Masking Stability analysis and generalization bounds of adversarial training

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T19:24:44.018546Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 653218af-38ae-4a40-b7ed-e618eecf5e7e · outbound

This paper cites Simple stochastic and online gradient descent algorithms for pairwise learning.

SeWA: Selective Weight Average via Probabilistic Masking Simple stochastic and online gradient descent algorithms for pairwise learning

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T19:24:44.001502Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 8354d197-1ed7-44d3-b486-cb0a70eabd47 · outbound

This paper cites Stagewise training accelerates convergence of testing error over sgd.

SeWA: Selective Weight Average via Probabilistic Masking Stagewise training accelerates convergence of testing error over sgd

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-07T19:24:43.401439Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1f94a4b9-88be-4840-bd21-40618da7cd0f · outbound

This paper cites Efficient denoising diffusion via probabilistic masking.

SeWA: Selective Weight Average via Probabilistic Masking Efficient denoising diffusion via probabilistic masking

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T19:24:43.972755Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 9abafd6c-599f-4950-9006-5e61527ccfcc · outbound

This paper cites Probabilistic bilevel coreset selection.

SeWA: Selective Weight Average via Probabilistic Masking Probabilistic bilevel coreset selection

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T19:24:43.955943Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 52a84fe4-e636-400d-b4cb-ad4f0d9bb417 · outbound

This paper cites Generalization Error Bounds with Probabilistic Guarantee for SGD in Nonconvex Optimization.

SeWA: Selective Weight Average via Probabilistic Masking Generalization Error Bounds with Probabilistic Guarantee for SGD in Nonconvex Optimization

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-07T19:24:43.415965Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a8afa1fd-5aab-4d8b-8011-179eac47808f · outbound

This paper cites Stability and generalization of the decentralized stochastic gradient descent ascent algorithm.

SeWA: Selective Weight Average via Probabilistic Masking Stability and generalization of the decentralized stochastic gradient descent ascent algorithm

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T19:24:43.786929Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Pith citing papers

Observation a51bac7d-2cd1-4656-bb84-1187399973da · inbound

Model Merging Scaling Laws in Large Language Models cites this paper.

Model Merging Scaling Laws in Large Language Models SeWA: Selective Weight Average via Probabilistic Masking

Reference 16

Resolution: verified exact; arxiv_id, observed 2026-05-18T13:32:37.735008Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.